© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27744
    Prev
    Next
    INDEX
    Explanations

    distortions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umerator
    -0.08
    次çļĦ
    -0.08
    注æĦıçļĦæĺ¯
    -0.08
    áĥĿáĥij
    -0.08
     اÙĦÙħتØŃدة
    -0.07
    ÙĪÙĬØ©
    -0.07
    -sama
    -0.07
    ÑģÑĤоÑĢа
    -0.07
    ÙĪÙĬات
    -0.07
    ä¹ħçļĦ
    -0.07
    POSITIVE LOGITS
    /stretch
    0.09
    ÑģÑı
    0.08
    ly
    0.08
    ×Ļף
    0.08
    äºĨçļĦ
    0.08
    Occurred
    0.08
    /ext
    0.08
    almas
    0.08
    uos
    0.07
    اÛĮÙĦ
    0.07
    Activations Density 0.012%

    No Known Activations